Deep Phase Correlation for End-to-End Heterogeneous Sensor Measurements Matching

Zexi Chen, Xuecheng Xu, Yue Wang, Rong Xiong
Proceedings of the 2020 Conference on Robot Learning, PMLR 155:2359-2375, 2021.

Abstract

The crucial step for localization is to match the current observation to the map. When the two sensor modalities are significantly different, matching becomes challenging. In this paper, we present an end-to-end deep phase correlation network (DPCN) to match heterogeneous sensor measurements. In DPCN, the primary component is a differentiable correlation-based estimator that back-propagates the pose error to learnable feature extractors, which addresses the problem that there are no direct common features for supervision. In addition, it eliminates the exhaustive evaluation in some previous methods, improving efficiency. With the interpretable modeling, the network is light-weighted and promising for better generalization. We evaluate the system on both the simulation data and Aero-Ground Dataset which consists of heterogeneous sensor images and aerial images acquired by satellites or aerial robots. The results show that our method is able to match the heterogeneous sensor measurements, outperforming the comparative traditional phase correlation and other learning-based methods. Code is available at https://github.com/jessychen1016/DPCN .

Cite this Paper

BibTeX
@InProceedings{pmlr-v155-chen21g, title = {Deep Phase Correlation for End-to-End Heterogeneous Sensor Measurements Matching}, author = {Chen, Zexi and Xu, Xuecheng and Wang, Yue and Xiong, Rong}, booktitle = {Proceedings of the 2020 Conference on Robot Learning}, pages = {2359--2375}, year = {2021}, editor = {Kober, Jens and Ramos, Fabio and Tomlin, Claire}, volume = {155}, series = {Proceedings of Machine Learning Research}, month = {16--18 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v155/chen21g/chen21g.pdf}, url = {https://proceedings.mlr.press/v155/chen21g.html}, abstract = {The crucial step for localization is to match the current observation to the map. When the two sensor modalities are significantly different, matching becomes challenging. In this paper, we present an end-to-end deep phase correlation network (DPCN) to match heterogeneous sensor measurements. In DPCN, the primary component is a differentiable correlation-based estimator that back-propagates the pose error to learnable feature extractors, which addresses the problem that there are no direct common features for supervision. In addition, it eliminates the exhaustive evaluation in some previous methods, improving efficiency. With the interpretable modeling, the network is light-weighted and promising for better generalization. We evaluate the system on both the simulation data and Aero-Ground Dataset which consists of heterogeneous sensor images and aerial images acquired by satellites or aerial robots. The results show that our method is able to match the heterogeneous sensor measurements, outperforming the comparative traditional phase correlation and other learning-based methods. Code is available at https://github.com/jessychen1016/DPCN .} }
Endnote
%0 Conference Paper %T Deep Phase Correlation for End-to-End Heterogeneous Sensor Measurements Matching %A Zexi Chen %A Xuecheng Xu %A Yue Wang %A Rong Xiong %B Proceedings of the 2020 Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2021 %E Jens Kober %E Fabio Ramos %E Claire Tomlin %F pmlr-v155-chen21g %I PMLR %P 2359--2375 %U https://proceedings.mlr.press/v155/chen21g.html %V 155 %X The crucial step for localization is to match the current observation to the map. When the two sensor modalities are significantly different, matching becomes challenging. In this paper, we present an end-to-end deep phase correlation network (DPCN) to match heterogeneous sensor measurements. In DPCN, the primary component is a differentiable correlation-based estimator that back-propagates the pose error to learnable feature extractors, which addresses the problem that there are no direct common features for supervision. In addition, it eliminates the exhaustive evaluation in some previous methods, improving efficiency. With the interpretable modeling, the network is light-weighted and promising for better generalization. We evaluate the system on both the simulation data and Aero-Ground Dataset which consists of heterogeneous sensor images and aerial images acquired by satellites or aerial robots. The results show that our method is able to match the heterogeneous sensor measurements, outperforming the comparative traditional phase correlation and other learning-based methods. Code is available at https://github.com/jessychen1016/DPCN .
APA
Chen, Z., Xu, X., Wang, Y. & Xiong, R.. (2021). Deep Phase Correlation for End-to-End Heterogeneous Sensor Measurements Matching. Proceedings of the 2020 Conference on Robot Learning, in Proceedings of Machine Learning Research 155:2359-2375 Available from https://proceedings.mlr.press/v155/chen21g.html.

Related Material